genbi

Turn a Wren project's context layer into a shareable, browser-side GenBI web app and deploy it to the user's Vercel or Cloudflare account. Orchestrates the full flow: `wren genbi build` returns a project-hydrated build instruction, the agent authors the app from scratch into apps/<name>/, then register → verify → deploy produce a shareable URL. Use this skill whenever the user wants to: build a dashboard from their Wren project, make a shareable analytics app, deploy their context layer as a web app, host a GenBI app on Vercel or Cloudflare Pages, or asks for a 'genbi app'.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content: every workflow step has copy-paste-ready commands, explicit validation checkpoints with error-recovery loops, and skill-specific knowledge rather than filler. The two moderate weaknesses are the repeated statement of the credentials rule and inlining of detailed troubleshooting sections that could live in reference files.

Suggestions

State the never-inline-credentials rule once in Safety boundaries and reference it from step 3 and step 5 instead of repeating it three times.

Move the Vercel Deployment Protection (401 trap) walkthrough into a references/ file (e.g. references/deploy-protection.md) and keep a two-line summary plus pointer in SKILL.md, keeping the main guide under the deployment step.

Consider the same treatment for the snapshot data-export recipe (references/data-export.md) so the core workflow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is dense and consistently adds Wren-specific knowledge Claude lacks (division of labor, data modes, the 401 trap), but the never-inline-credentials rule is stated three times (step 3, step 5, Safety boundaries) — minor repetition that could be trimmed to a single authoritative statement plus one pointer.	4 / 5
Actionability	Every step ships an executable command ('wren genbi build <name> --prompt … --data-mode <mode>', register, verify, deploy, open, list/remove), the DuckDB→parquet snippet is real runnable Python, and a Quick Reference table consolidates all commands; placeholders like <name>/<db> are standard CLI parameters, not pseudocode.	5 / 5
Workflow Clarity	A clearly sequenced five-step workflow with explicit validation gates and feedback loops: preconditions, 'If verify fails: fix the reported problems and re-run verify. Do NOT proceed to deploy on a failed verify', local preview via 'wren genbi open', and post-deploy URL verification before calling a link shareable.	5 / 5
Progressive Disclosure	A single-file skill (no references/, scripts/, or assets/ exist) with clean headers, a scoped snapshot-export subsection, and a quick-reference table; well organized, but detailed troubleshooting content (the Vercel 401-trap section and export recipe) is inlined where a one-level reference file split would keep SKILL.md leaner.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete, comprehensive, third-person, with an explicit 'Use this skill whenever…' trigger clause enumerating natural user phrasings. Its only weakness is a few missing natural synonyms, which keeps trigger coverage just short of exhaustive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'turn a Wren project's context layer into a shareable, browser-side GenBI web app', 'deploy it to the user's Vercel or Cloudflare account', 'register → verify → deploy' — with comprehensive coverage and no gaps; third-person voice is used throughout.	5 / 5
Completeness	Explicitly answers both what (the first two sentences name the capability and the orchestrated flow) and when ('Use this skill whenever the user wants to: build a dashboard…, make a shareable analytics app…, or asks for a "genbi app"') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ('build a dashboard from their Wren project', 'make a shareable analytics app', 'host a GenBI app on Vercel or Cloudflare Pages', "'genbi app'") with synonyms across deployment verbs and providers, but a few natural variations (e.g. 'share/publish my dashboard', 'Wren data') are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Wren project → GenBI app → Vercel/Cloudflare) with all triggers gated on it; minimal overlap risk with generic dashboard or document skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: Canner/WrenAI
Path: core/wren/src/wren/skills_content/genbi/SKILL.md
Commit: 2cc843f

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.